结合变异系数法和机器学习模型的棉花长势监测

doi:10.13474/j.cnki.11-2246.2024.0720

测绘通报 ›› 2024, Vol. 0 ›› Issue (7): 111-116.doi: 10.13474/j.cnki.11-2246.2024.0720

结合变异系数法和机器学习模型的棉花长势监测

杨思佳^1,2, 王仁军^1,2, 郑江华^1,2, 赵鹏玉^1,2, 韩万强^1,2, 毛旭芮^1,2, 范宏^1,2

1. 新疆大学地理与遥感科学学院, 新疆乌鲁木齐 830046;
2. 新疆大学绿洲重点实验室, 新疆乌鲁木齐 830046

收稿日期:2023-11-22 发布日期:2024-08-02
通讯作者: 郑江华。E-mail:zheng.jianghua@xju.edu.cn
作者简介:杨思佳(1999—),男,硕士,主要从事农业遥感研究。E-mail:yangsijia_2021@163.com
基金资助:
新疆生产建设兵团第七师棉花长势遥感监测(202105140019)

Cotton growth monitoring combined with coefficient of variation method and machine learning model

YANG Sijia^1,2, WANG Renjun^1,2, ZHENG Jianghua^1,2, ZHAO Pengyu^1,2, HAN Wanqiang^1,2, MAO Xurui^1,2, FAN Hong^1,2

1. College of Geography and Remote Sensing Sciences, Xinjiang University, Urumqi 830046, China;
2. Xinjiang Key Laboratory of Oasis Ecology, Xinjiang University, Urumqi 830046, China

Received:2023-11-22 Published:2024-08-02

摘要/Abstract

摘要： 为了更加准确地获取棉花关键物候期的长势信息,本文首先通过棉花制图指数提取棉花种植区域;然后利用变异系数法将反映棉花长势的株高、SPAD值、叶片湿重、叶片干重与叶面积5种指标构建为一个综合长势指标,即棉花长势指数(FBCGI);最后选取最优特征变量,结合随机森林模型构建棉花长势反演模型。结果表明:① 棉花总体分类精度达到81.65%;② 与5种单一长势指标相比,构建的FBCGI与植被指数的相关性更高;③基于最优特征变量和随机森林模型构建的棉花长势监测模型,在建模集和验证集中的R²和RMSE分别为0.74、0.07和0.51、0.10。研究结果可为棉花长势监测提供重要参考。

关键词: 棉花, 棉花制图指数, 综合长势监测, 遥感

Abstract: In order to obtain the growth information of the key phenological period of cotton more accurately, the cotton planting area is extracted through the cotton mapping index. Secondly, five indexes, including plant height, SPAD value, leaf wet weight, leaf dry weight and leaf area, reflecting cotton growth, are constructed into a comprehensive growth Index, namely Flowering and boll cotton growth index (FBCGI), using the coefficient of variation method. Finally, the optimal characteristic variables are selected and the inverse model of cotton growth is constructed by combining with random forest model. The results showed that: ①The overall classification accuracy of cotton reached 81.65%.②Compared with the five single growth indicators, the constructed FBCGI had a higher correlation with vegetation index. ③The R² and RMSE of the cotton growth monitoring model based on the optimal characteristic variables and random forest model in the modeling set and validation set are 0.74, 0.07 and 0.51, 0.10, respectively. The results can provide important reference for cotton growth monitoring.

Key words: cotton, cotton mapping index, comprehensive growth monitoring, remote sensing

中图分类号:

P208

杨思佳, 王仁军, 郑江华, 赵鹏玉, 韩万强, 毛旭芮, 范宏. 结合变异系数法和机器学习模型的棉花长势监测[J]. 测绘通报, 2024, 0(7): 111-116.

YANG Sijia, WANG Renjun, ZHENG Jianghua, ZHAO Pengyu, HAN Wanqiang, MAO Xurui, FAN Hong. Cotton growth monitoring combined with coefficient of variation method and machine learning model[J]. Bulletin of Surveying and Mapping, 2024, 0(7): 111-116.

参考文献

[1] 肖海峰,俞岩秀.中国棉花生产布局变迁及其比较优势分析[J].农业经济与管理,2018(4):38-47.
[2] 李志鹏,万素梅,胡守林,等.不同灌水频率和灌溉定额对南疆无膜棉蕾铃时空分布及产量形成的影响[J].棉花学报,2022,34(5):383-400.
[3] 杨邦杰,裴志远.农作物长势的定义与遥感监测[J].农业工程学报,1999,15(3):214-218.
[4] 单捷,孙玲,王志明,等.GF-1影像遥感监测指标与冬小麦长势参数的关系[J].江苏农业学报,2019,35(6):1323-1333.
[5] 王乐,樊彦国,樊博文,等.基于高分卫星的冬小麦长势监测及驱动因素分析[J].灌溉排水学报,2023,42(5):24-32.
[6] 裴浩杰,冯海宽,李长春,等.基于综合指标的冬小麦长势无人机遥感监测[J].农业工程学报,2017,33(20):74-82.
[7] 徐云飞,程琦,魏祥平,等.变异系数法结合优化神经网络的无人机冬小麦长势监测[J].农业工程学报,2021,37(20):71-80.
[8] 刘晓晨.基于Landsat 8遥感数据的棉花长势快速监测[J].新疆农业科技,2015(6):50.
[9] 刘灵,张加龙,韩雪莲,等.基于GEE和Sentinel时序影像的优势树种识别研究[J].森林工程,2023,39(1):63-72,81.
[10] XUN Lan,ZHANG Jiahua,CAO Dan,et al.A novel cotton mapping index combining Sentinel-1 SAR and Sentinel-2 multispectral imagery[J].ISPRS Journal of Photogrammetry and Remote Sensing,2021,181:148-166.
[11] ZENG Linglin,WARDLOW B D,XIANG Daxiang,et al.A review of vegetation phenological metrics extraction using time-series,multispectral satellite data[J].Remote Sensing of Environment,2020,237:111511.
[12] RADOČAJ D,ŠILJEG A,MARINOVIĆ R,et al.State of major vegetation indices in precision agriculture studies indexed in web of science:a review[J].Agriculture,2023,13(3):707.
[13] ZAHIR S A D M,JAMLOS M F,OMAR A F,et al.Review-plant nutritional status analysis employing the visible and near-infrared spectroscopy spectral sensor[J].Spectrochimica Acta Part A:Molecular and Biomolecular Spectroscopy,2024,304:123273.
[14] SEGARRA J,BUCHAILLOT M L,ARAUS J,et al.Remote sensing for precision agriculture:Sentinel-2 improved features and applications[J].Agronomy,2020,10(5):641.
[15] AYU PURNAMASARI R,NOGUCHI R,AHAMED T.Land suitability assessments for yield prediction of cassava using geospatial fuzzy expert systems and remote sensing[J].Computers and Electronics in Agriculture,2019,166:105018.
[16] MUHAMAT A A,ZULKIFLI A F,IBRAHIM M A,et al.Realising the corporate social performance (CSP) of takaful (islamic insurance) operators through drone-assisted disaster victim identification (DVI)[J].Sustainability,2022,14(9):5440.
[17] QIU Ruonan,LI Xing,HAN Ge,et al.Monitoring drought impacts on crop productivity of the U.S.Midwest with solar-induced fluorescence:GOSIF outperforms GOME-2 SIF and MODIS NDVI,EVI,and NIRv[J].Agricultural and Forest Meteorology,2022,323:109038.
[18] PALIWAL A,Balwinder-Singh,POONIA S,et al.Using microsatellite data to estimate the persistence of field-level yield gaps and their drivers in smallholder systems[J].Scientific Reports,2023,13:11170.
[19] STEPHEN S,HALDAR D,PATEL N R.Impact of various vegetation indices on mango orchard mapping using object-based image analysis[J].Journal of Geomatics,2022,16(2):159-166.
[20] DAMM A,COGLIATI S,COLOMBO R,et al.Response times of remote sensing measured Sun-induced chlorophyll fluorescence,surface temperature and vegetation indices to evolving soil water limitation in a crop canopy[J].Remote Sensing of Environment,2022,273:112957.
[21] CARLSON T N,RIPLEY D A.On the relation between NDVI,fractional vegetation cover,and leaf area index[J].Remote Sensing of Environment,1997,62(3):241-252.
[22] CUI Kailong,YANG Jilin,DONG Jinwei,et al.Comparing different spatial resolutions and indices for retrieving land surface phenology for deciduous broadleaf forests[J].Remote Sensing,2023,15(9):2266.
[23] KIM Y,JACKSON T,BINDLISH R,et al.Radar vegetation index for estimating the vegetation water content of rice and soybean[J].IEEE Geoscience and Remote Sensing Letters,2012,9(4):564-568.
[24] QI J,CHEHBOUNI A,HUETE A R,et al.A modified soil adjusted vegetation index[J].Remote Sensing of Environment,1994,48(2):119-126.
[25] 巨喜锋,林峻,吴建国,等.新疆典型蝗虫适生区分布预测[J].生态学报,2022,42(21):8605-8617.

结合变异系数法和机器学习模型的棉花长势监测

Cotton growth monitoring combined with coefficient of variation method and machine learning model

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	王霞迎, 折育霖, 张双成, 夏元平, 牛玉芬. 基于Sentinel-1和Landsat 8遥感数据的高原地区土壤水分反演[J]. 测绘通报, 2024, 0(7): 140-146.
[2]	范强, 孙爽, 孙虎虎. 资源枯竭型城市生态质量时空格局与驱动力研究——以阜新市中心城区为例[J]. 测绘通报, 2024, 0(6): 24-29.
[3]	刘卫南, 宋红克, 李清波, 谢谟文. 利用光学影像的滑坡位移监测[J]. 测绘通报, 2024, 0(6): 41-45,64.
[4]	马姗姗, 杨嘉葳, 王继燕, 熊俊楠. 基于光谱特征的城市水体提取[J]. 测绘通报, 2024, 0(6): 71-76.
[5]	张伟, 张朝龙, 王本林, 蔡安宁. 基于深度学习的多尺度无人机遥感图像道路提取[J]. 测绘通报, 2024, 0(6): 77-81.
[6]	王丽霞, 喜文飞, 史正涛, 赵子龙, 钱堂慧, 赵磊, 马奕捷. 深度学习滑坡识别算法中样本不平衡问题的研究[J]. 测绘通报, 2024, 0(5): 12-18.
[7]	郭松涛, 邢帅, 张国平, 孔瑞瑶, 陈丽. 异构卫星遥感数据融合的水深反演模型[J]. 测绘通报, 2024, 0(5): 19-23.
[8]	李淑, 李鹏, 李振洪, 王厚杰. 协同全极化SAR与光学遥感的潮沟精细提取方法[J]. 测绘通报, 2024, 0(5): 29-34,40.
[9]	康娟, 方贺, 石守海, 夏瑞, 彭金灵. 阿克苏地区天然林保护工程区植被覆盖度变化及驱动因子研究[J]. 测绘通报, 2024, 0(5): 41-47.
[10]	王陈哲, 刘昭贤, 付利钊. 高光谱遥感技术在耕地质量反演中的应用[J]. 测绘通报, 2024, 0(5): 127-132.
[11]	张楠, 张蕴灵. 基于深度学习模型的复杂困难路网提取方法[J]. 测绘通报, 2024, 0(5): 155-159.
[12]	焦晓萌, 张兵, 高阳, 郑铭轩, 周岩, 况玮婕. 利用改进型遥感生态指数的岩溶区生态环境质量评价[J]. 测绘通报, 2024, 0(4): 54-60.
[13]	张翠兰, 曹香芹, 冀琴. 1990—2020年冬克玛底流域冰川变化遥感监测[J]. 测绘通报, 2024, 0(4): 61-68.
[14]	张兰兰, 王红雷. 基于深度学习的耕地非农化遥感监测与时空分析——以开阳县为例[J]. 测绘通报, 2024, 0(3): 13-18.
[15]	马锦山, 贾国焕, 张赛, 张炯. 基于多源高分辨率遥感影像的典型自然资源要素提取[J]. 测绘通报, 2024, 0(3): 123-126,150.